简体中文
繁體中文
English
Français
Русский
日本語
Tiếng Việt
한국어
Deutsch
Español
Italiano
Português
العربية
ไทย
Bahasa Indonesia
Bahasa Melayu
Türkçe
Polski
Nederlands
Dansk
Norsk
Қазақшаdeepseek-v4-flashDeepSeek V4 Flash pricing (October 2026)
DeepSeek lists DeepSeek V4 Flash at $0.30 per 1M input tokens and $1.20 per 1M output tokens.
On Crazyrouter the same model is $0.23 / $0.67 — 23% below list price.
That is $0.0003 / $0.0012 per 1K tokens. DeepSeek V4 Flash is the #5 cheapest of the 38 chat models we track, by input price. 4.4× cheaper than DeepSeek V4 Pro. Through Crazyrouter you save $0.07 on every 1M input tokens versus list.
Call DeepSeek V4 Flash at $0.23 in / $0.67 out per 1M tokens. Same model, same API, no plan — pay per token.
Sign up → try this model with $2 Playground credit. For API calls, add funds and create an API key; Playground credit cannot pay for API calls.
Looking for the ChatGPT / Claude app subscription price? That is a separate consumer product sold by DeepSeek. This page is the developer API price per token.
DeepSeek V4 Flash price by provider
USD per 1M tokens. Cloud prices are the base tier in the default region; the linked source is authoritative.
| Provider | Input | Cached input | Output | Context | Source |
|---|---|---|---|---|---|
| DeepSeek | $0.30 | $0.006 | $1.20 | 1M | DeepSeek |
| Azure | $0.19 | $0.028 | $0.51 | 1M | Azure AI Foundry |
| AWS Bedrock | No verified quote | ||||
| Google Vertex AI | No verified quote | ||||
| OpenRouter | No verified quote | ||||
| Crazyrouter | $0.23 | $0.01 | $0.67 | 1M | crazyrouter.com |
per 1M tokens · Snapshot Oct 24, 2026
What DeepSeek V4 Flash costs per month
Three typical workloads, priced on each provider from the table above.
| Workload | DeepSeek | Azure | Crazyrouter |
|---|---|---|---|
| Prototype: 10M in / 2M out | $5.40 | $2.92 | $3.64 |
| Product: 100M in / 20M out | $54.00 | $29.20 | $36.40 |
| Scale: 1B in / 200M out | $540.00 | $292.00 | $364.00 |
Price changes
- Oct 9, 2026 — OpenRouter: $0.03 / $1.28 → $0.0075 / $1.28 per 1M
- Oct 7, 2026 — OpenRouter: $0.0224 / $1.28 → $0.03 / $1.28 per 1M
- Oct 5, 2026 — OpenRouter: $0.028 / $0.056 → $0.0224 / $1.28 per 1M
- Oct 3, 2026 — OpenRouter: $0.0419 / $0.0837 → $0.028 / $0.056 per 1M
- Oct 2, 2026 — OpenRouter: $0.0785 / $0.157 → $0.0419 / $0.0837 per 1M
- Oct 1, 2026 — OpenRouter: $0.14 / $0.28 → $0.0785 / $0.157 per 1M
- Sep 28, 2026 — OpenRouter: $0.047 / $0.0941 → $0.14 / $0.28 per 1M
- Sep 11, 2026 — DeepSeek: $0.44 / $1.32 → $0.30 / $1.20 per 1M
- Aug 19, 2026 — DeepSeek: $0.14 / $0.28 → $0.44 / $1.32 per 1M
- Jun 17, 2026 — DeepSeek started listing DeepSeek V4 Flash at $0.14 / $0.28 per 1M.
- Jun 12, 2026 — Azure started listing DeepSeek V4 Flash at $0.19 / $0.51 per 1M.
Alternatives to DeepSeek V4 Flash
Same-family models and cheaper options for similar tasks.
DeepSeek V4 Flash pricing FAQ
How much does DeepSeek V4 Flash cost?
DeepSeek charges $0.30 per 1M input tokens and $1.20 per 1M output tokens. Through Crazyrouter the same model is $0.23 / $0.67.
What is cached input pricing?
Tokens that repeat an earlier prompt prefix are billed at the cached rate ($0.006 per 1M when supported) instead of the full input price.
Is there a batch discount?
No public batch tier is listed for DeepSeek V4 Flash; Crazyrouter's per-token price applies to all requests.
Is DeepSeek V4 Flash cheaper on Azure, Bedrock or Vertex?
Cloud providers usually match the list price and add regional or provisioned tiers; see the table above for the base rate on each. Crazyrouter applies its discount on top of list.
Sources and method
Provider reference prices use LiteLLM data and maintained entries. Provider links are references, not proof of daily official verification. Snapshot: Oct 24, 2026. Crazyrouter rates come from our billing table; confirm current prices, region and terms with the provider before purchase.
- DeepSeek — api-docs.deepseek.com/quick_start/pricing
- Azure — azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service
- Crazyrouter — crazyrouter.com/pricing
- LiteLLM